© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198920
    Prev
    Next
    INDEX
    Explanations

    household

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ség
    1.06
    ről
    1.03
    t
    0.99
    től
    0.91
    s
    0.89
    스
    0.88
    ри
    0.86
     sparsely
    0.82
     blossomed
    0.79
    tól
    0.79
    POSITIVE LOGITS
    T
    1.41
    O
    1.34
    W
    1.20
    E
    1.17
    ک
    0.96
    M
    0.96
    S
    0.95
     institu
    0.94
    IC
    0.93
    V
    0.93
    Activations Density 0.003%

    No Known Activations